© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 58168
    Prev
    Next
    INDEX
    Explanations

    native

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å®ŀè´¨
    -0.30
    nob
    -0.27
    å°ij
    -0.26
    ä¸Ĭå¸Ĥåħ¬åı¸
    -0.26
    ä¸ŃåĽ½äºº
    -0.26
    çİīçŁ³
    -0.26
    羣æŃ£åģļåĪ°
    -0.26
    opoulos
    -0.26
    auga
    -0.25
     radical
    -0.25
    POSITIVE LOGITS
    ecal
    0.31
     mañana
    0.28
    MediaType
    0.27
    efs
    0.24
    çĶŁçī©
    0.23
     interrupted
    0.23
    escal
    0.23
    s
    0.23
     phys
    0.23
     organis
    0.23
    Activations Density 0.004%

    No Known Activations